LangGraph is a domain-agnostic multi-agent framework that aims to provide reusable LangChain tools and an MCP (Model Context Protocol) backend (memory, search (RAG), HTTP, scheduler, notifications, authentication, logging). You might find the flight search agent example particularly helpful.
- capability exposure inferred + 32
- recent drift inferred + 12
- tool safety inferred + 5
inferred
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
graded 9m ago · see ecosystem CVEs →
- B · 32 → C · 49
No known CVEs for this server.
- medium dangerous code
dynamic exec: __import__ sink
analyzed commit df2e988 · analyzer v28 · 4h ago
skills & prompt files 1
danger signals2
- dynamic code execution __import__ sink ace19-dev-agentic-ai-common-tools-df2e988/examples/flight_monitor/run.py :668
_SCAN_WORKERS = int(__import__("os").environ.get("SCAN_WORKERS", "4")) - suspicious endpoint api.telegram.org ace19-dev-agentic-ai-common-tools-df2e988/services/notification.py :165
url = f"https://api.telegram.org/bot{token}/sendMessage"
- recent drift +12 capability drift →
[](https://mcpobservatory.com/servers/github:ace19-dev/agentic-ai-common-tools/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of ace19-dev.